What is multi-mcp CLAUDE.md?

Project instructions for Multi-MCP, a Python proxy that connects one MCP server to several other MCP servers and routes requests between them. MCP, or Model Context Protocol, lets an AI assistant communicate with external tools.

Understanding or modifying Multi-MCP components, including backend connections, standard input/output and HTTP event transports, runtime server changes, and tool name separation.

They explain the repository's architecture and conventions so changes fit its proxy, client, transport, logging, and tool-naming design.

How kfirtoledo/multi-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kfirtoledo/multi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kfirtoledo/multi-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kfirtoledo/multi-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kfirtoledo/multi-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kfirtoledo/multi-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kfirtoledo/multi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kfirtoledo/multi-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kfirtoledo/multi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kfirtoledo/multi-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,483 This file is loaded in full into every session.

When invoked 2,483 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02483	$0.02483
Opus 5.5	$0.00993	$0.00993
Sonnet 5.5	$0.00497	$0.00497
Haiku 4.5	$0.00248	$0.00248

Measured 2mo ago against content hash b8128abe190c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

multi-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Multi-MCP is a Python-based proxy server that acts as a single MCP (Model Context Protocol) server while connecting to and routing between multiple backend MCP servers. It supports both STDIO and SSE (Server-Sent Events) transports and can dynamically add/remove MCP servers at runtime.

Architecture

Core Components

MultiMCP (src/multimcp/multi_mcp.py): Main server orchestrator that handles configuration, transport modes, and HTTP endpoints
MCPProxyServer (src/multimcp/mcp_proxy.py): Core proxy that forwards MCP requests to backend servers, handles tool namespacing (server_name_tool_name), and manages capabilities aggregation
MCPClientManager (src/multimcp/mcp_client.py): Manages lifecycle of multiple MCP client connections (both stdio and SSE)
Logger (src/utils/logger.py): Centralized logging using Rich handlers with multi_mcp.* namespace

Key Patterns

Tool Namespacing: Tools are namespaced as server_name_tool_name to avoid conflicts when multiple servers expose tools with the same name
Transport Flexibility: Supports both STDIO (for CLI/pipe-based) and SSE (for HTTP/network-based) communication
Dynamic Server Management: Can add/remove MCP servers at runtime via HTTP API (SSE mode only)
Capability Aggregation: Proxies and combines tools, prompts, and resources from all connected backend servers

Development Commands

Running the Server

# STDIO mode (default)
uv run main.py --transport stdio

# SSE mode with custom host/port
uv run main.py --transport sse --host 0.0.0.0 --port 8080

# With custom config file
uv run main.py --config ./examples/config/mcp_k8s.json

# Quick development run
make run

Testing

# Individual test suites
make test-proxy      # Core proxy functionality  
make test-e2e        # End-to-end integration tests
make test-lifecycle  # Client lifecycle management
make test-k8s        # Kubernetes deployment tests (requires docker-build)

# All tests
make all-test

# Run specific test file directly
pytest -s tests/proxy_test.py

Read the full file on GitHub · 250 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 250 lines · 2,483 tokens per session scan A b8128abe190c

Subscribe to this mod's changes

multi-mcp CLAUDE.md is an instructions file published in the GitHub repository kfirtoledo/multi-mcp (111 stars, last pushed 1y ago), licensed MIT. It adds 2,483 tokens to every session, about $0.0099 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs

multi-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
multi-mcp CLAUDE.mdkfirtoledo/multi-mcp	Instructions file	111	1y ago	MIT	A	2,483	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

multi-mcp: Instructions file for Claude Code